Fusion scheme for automatic and large-scaled built-up mapping

Yann Forget, Michal Shimoni, Juanfran Lopez, Catherine Linard, Marius Gilbert

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

As more and more geospatial data are produced, Big Earth data is becoming a new key to the understanding of the Earth. Such opportunity also comes with new issues and challenges related to the massive and heteregenous amount of data to process and to analyse. The present work explores the use of three types of Earth Observation (EO) data in order to automatically classify built and non-built areas in Africa using a machine learning classifier: SAR (Sentinel) and optical (Landsat) imagery, and the OpenStreetMap (OSM) database as training data. Experimental results in ten african cities show that the use of satellite data from multiple sensors improves the performance of the classifiers in these areas. They also show that using crowd-sourced geospatial databases such as OSM as training data leads to similar accuracies than when relying on field surveys or hand-digitalized datasets.

Original languageEnglish
Title of host publication2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2072-2075
Number of pages4
ISBN (Electronic)9781538671504
DOIs
Publication statusPublished - 31 Oct 2018
Event38th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Valencia, Spain
Duration: 22 Jul 201827 Jul 2018

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume2018-July

Conference

Conference38th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018
Country/TerritorySpain
CityValencia
Period22/07/1827/07/18

Fingerprint

Dive into the research topics of 'Fusion scheme for automatic and large-scaled built-up mapping'. Together they form a unique fingerprint.

Cite this